The paper presents CoEvolve, a framework for executable coordination of multi-robot teams.
CoEvolve introduces a novel approach to executable coordination that adapts to changes in the environment and enables robots to work together more effectively.
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
Recent advances in Vision-Language-Action (VLA) models and World Action Models (WAMs) have expanded the manipulation and whole body capabilities of individual robots. Yet a single robot remains limited by its embodiment, and many real world tasks require capabilities that can only emerge through cooperation. Existing multi robot frameworks largely emphasize task decomposition, allocation, and replanning, while providing limited support for adapting executable coordination when physical execution deviates from the intended behavior. We present CoEvolve, a framework that represents team coordination as executable code over fixed robot motor skills. CoEvolve introduces Verifier Guided Coordination Evolution, where a multimodal foundation model instantiates coordination strategies through motion primitives, semantic objectives, temporary robot roles, and bounded execution parameters. Physical verification evaluates each executed transition, rejected behaviors trigger structured coordination revision from an accepted checkpoint, and verified experience is retained to guide subsequent decisions. We evaluate CoEvolve with two simulated Unitree G1 humanoids transporting a freely supported rigid payload through constrained corridors. Across 15 base task runs with three multimodal backbone families, CoEvolve completes 8 tasks, with every backbone achieving end to end success. Additional evaluations yield verified placement on two additional corridor layouts and after both same-backbone and cross-backbone experience initialization, while exposing persistent limitations in motion precision and contact stability. These results support executable coordination as a practical interface for adapting long horizon multi robot collaboration under shared physical constraints.
Robot-Task Suitability in Heterogeneous Multi-Robot Task Allocation
This paper compares ten deterministic and two LLM-based methods for estimating r…
What Robots Do Matters More Than What They Look Like: Task Context Shapes Trust in Educational HRI
This study examines how robot appearance and task type influence trust in robots…
Do Self-Evolving Skills Generalize to Held-Out Tasks?
This paper investigates the generalizability of self-evolving skills in AI agent…
Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven…
This paper develops a simulator for tendon-driven continuum robots that unifies…
Federated Agentic AI for Interference-Aware Adaptive Spectrum Coordination
This paper proposes a federated multi-agent deep reinforcement learning framewor…
EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning
This paper introduces EgoLAP, a framework that learns from human and robot traje…
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
This paper introduces DexPort, a portable data-collection interface for high-DoF…
Whole-Body Impedance Model Predictive Control for Safe Physical Human--Robot Interaction on Floating…
This paper proposes a three-level control architecture for floating-base robots…